Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 5
    Prev
    Next
    INDEX
    Explanations

    anatomical features and specifications related to surfaces and textures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Glej
    -0.40
     محفوظة
    -0.38
    HostException
    -0.35
    msgSender
    -0.34
    AccessFile
    -0.33
    HTTPClient
    -0.32
    __":
    
    -0.31
    FactoryBean
    -0.31
    SequentialGroup
    -0.31
    новниш
    -0.30
    POSITIVE LOGITS
     wrinkle
    0.72
     wrinkles
    0.71
     embossed
    0.69
     wrinkled
    0.69
     wrink
    0.66
     emboss
    0.66
     grooves
    0.65
     ridges
    0.63
     groove
    0.61
     depressions
    0.60
    Activations Density 0.322%

    No Known Activations